High-signal AI/security/automation notes.
NVIDIA patched two vulnerabilities in NemoClaw: CVE-2026-24222 (CVSS 8.6) lets prompt-injected content exfiltrate host environment variables through a sandbox initialization flaw, and CVE-2026-24231 (CVSS 5.9) enables SSRF via crafted endpoint URLs.
CIS publishes three companion guides mapping CIS Controls v8.1 to LLMs, AI agents, and Model Context Protocol environments, giving security teams a familiar framework for governing agentic AI.
Oasis Security discovered three chained vulnerabilities in Claude.ai — invisible prompt injection via URL parameters, data exfiltration, and an open redirect — creating a complete attack pipeline against default sessions.
CVE-2026-26268 shows how AI coding agents in Cursor IDE can be tricked into executing arbitrary code via malicious Git hooks embedded in untrusted repositories.
OpenAI and Anthropic met with the White House national cyber director, Congress, and federal agencies to propose deploying frontier AI models for government cybersecurity operations.
ReversingLabs traces a North Korean-linked supply chain attack where a Claude Opus co-authored commit introduced PromptMink malware into an npm crypto trading agent.
CVE-2026-7593 exposes OS command injection in the Sunwood-ai-labs command-executor-mcp-server, an unpatched MCP tool integration that allows remote arbitrary command execution.
UK AI Safety Institute evaluates GPT-5.5 at 71.4% on Expert-tier cyber tasks, with a universal jailbreak found in six hours.
New arXiv paper benchmarks DKnownAI Guard against AWS Bedrock Guardrails, Azure Content Safety, and Lakera Guard across recall and false-positive metrics.
First large-scale empirical study of indirect prompt injections on the web identifies 15.3K validated instances across 11.7K pages, with compliance rates up to 8% on smaller models.
Palo Alto Networks announces acquisition of Portkey, positioning the AI Gateway as a mission-critical control plane for autonomous agent communications and security.
Netflix security engineers Scott Behrens and Justice Cassel present "Source to Sink: Improving LLM Vuln Discovery" at [un]prompted 2026, covering end-to-end approaches for finding vulnerabilities in large language model systems.
Anthropic launches Claude Security in public beta, an AI-powered tool that scans codebases for vulnerabilities and suggests patches for enterprise customers.
CVE-2026-41686 is a medium-severity flaw in the Anthropic TypeScript SDK where BetaLocalFilesystemMemoryTool creates world-readable memory files, risking agent state exposure.